Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
MCP is an open protocol that enables AI models to securely interact with local and remote resources through standardized server implementations.
Model Context Protocol server for fetching web content and processing images. This allows Claude Desktop (or any MCP client) to fetch web content and handle images appropriately.
A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents
Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs
MCP Server for Burp
A Model Context Protocol (MCP) server that reads and writes MS Excel data
Inspect schemas and run controlled read queries against PostgreSQL databases.
A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
A Model Context Protocol (MCP) server that helps large language models index, search, and analyze code repositories with minimal setup
Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
Published in CNCF Landscape: A MCP server for Kubernetes.
The Typescript MCP Framework
Agent Skills
Give your coding agent a complete map of the OpenClaw environment. Config · Logs · Cron Jobs · Sessions · Skills · Docs — no exploring from scratch.
The open-source cockpit for AI coding agents. Map your repo, control what your agents can touch, and see what changed before you ship.
A collection of agent skills for structured, GitHub-centric development.
CLI for Chunk — inner loop validation for software teams building with AI agents.
Skills for agents.
致你忘不掉的那个TA，你们干大模型都是码圣 It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
Codex-first, vendor-neutral RTL coding and verification skill using open-source tools
Copy this repo into any project. Claude Code, Codex, and other agentic tools then follow the same gated process — spec, plan, task cards, implementation, verification, review — before code reaches...
Rust-first autonomous agent runtime with functional parity goals against NousResearch/hermes-agent, plus an Ultra reliability, security, and operator-control layer.
Commonplace studies how agentic systems can change after deployment through inspectable knowledge artifacts.
MBA AI Agent课程：2天集中培训，从LLM基础到多智能体系统
TavernWeave 是面向 Codex 与 Claude Code、并为 DeepSeek Harness 提供实验适配的 SillyTavern 制卡与 Vibe Coding 工程系统：20 个可路由 Skill、从模糊愿望到总设计案/首版/蓝图的项目编排、可再次核验且不可改写的本地成长履历、一份可恢复的创作权威、一条从源码到真实宿主和人工验收的证据链、统一随包的...